Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    chemical compounds and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -anchor
    -0.14
    esan
    -0.13
    ç¾İ
    -0.13
     metav
    -0.13
    ANDLE
    -0.12
    ýš
    -0.12
    roj
    -0.12
    ä¿
    -0.12
    ARRANT
    -0.12
    ÛĮÙĨÙĩ
    -0.12
    POSITIVE LOGITS
    輯
    0.14
     ActionTypes
    0.14
     
    0.14
    quential
    0.13
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.13
     Matthias
    0.13
     Fran
    0.13
    clave
    0.13
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.13
     Tu
    0.13
    Act Density 0.466%

    No Known Activations